Designing a Voting Mechanism in the GroupFun Music Recommender System

Abstract

In this paper we present the implementation of a truthful preference elicitation algorithm that favors item diversity in our group music recommender system, GroupFun. First, we discuss our methodology and relate to other group decision mechanisms already implemented in state of the art group recommender systems. Then, we formalize the implementation of the probabilistic weighted sum algorithmic in GroupFun. In addition to this we discuss user strategies and incentives for submitting ratings and show how PWS favors music diversity maximizing the group's overall satisfaction. Due to space constraints in the following we highlight only the main characteristics of our system presenting its design, interfaces and user actions. © Springer-Verlag Berlin Heidelberg 2013.